Concepts
Feature Engineering
The process of transforming and selecting what data should be fed into your model is often called feature engineering.
Model Training
Selecting the right algorithm for the job using the processed data from feature engineering.
Hyperparameter Tuning
Machine learning models have parameters that are tuned in the model training step. Most ML models also have another set of parameters called hyperparameters that can be modified prior to training.
These parameters can heavily influence the performance of your resulting ML model and need to be tuned properly. There are good tools to help automate that process.
Model Serving
Trained models deployment
Supervised Learning
Few-shot Learning
The model learns the task based on a few samples. The samples are similar to the task we want the model to solve and specify the input and desired output.
Zero-shot Learning
The model learns the task without any samples based only on the task description.
Unsupervised Learning
Dimensionality reduction
They are needed whenever you want to visualize data with more than two or three features (i.e. dimensions).
- Dimensionality Reduction (opens in a new tab)
- t-SNE and UMAP projections in Python (opens in a new tab)